Abstract
A vast majority of epileptic seizure (ictal) detection on electroencephalogram (EEG) data has been retrospective. Therefore, even though some may include many patients and extensive evaluation benchmarking, they all share a heavy reliance on labelled data. This is perhaps the most significant obstacle against the utility of seizure detection systems in clinical settings. Most retrospectively tested algorithms under-perform when presented with real-world data with different outcomes than those obtained during their training. Another critical challenge is hitting the right balance between sensitivity and false alarms. It is common to hear about tools developed for automated seizure labelling with low or extremely low sensitivities and high or too high false alarm rates. We argue that while achieving the best sensitivity may not be possible alongside the best false alarm rate, hitting the right balance is crucial. In this paper, we present a prospective automatic ictal detection and labelling performed at the level of a human expert (arbiter) and reduces labelling time by more than an order of magnitude. Accurate seizure detection and labelling are still a time-consuming and cumbersome task in epilepsy monitoring units (EMUs) and epilepsy centres, particularly in countries with limited facilities and insufficiently trained human resources. This work implements a convolutional long short-term memory (ConvLSTM) network that is pre-trained and tested on Temple University Hospital (TUH) EEG corpus. It is then deployed prospectively at the Comprehensive Epilepsy Service at the Royal Prince Alfred Hospital (RPAH) in Sydney, Australia, testing nearly 14,590 hours of EEG data across nine years. Our system prospectively labelled RPAH epilepsy ward data and subsequently reviewed by two neurologists and three certified EEG specialists. Our clinical result shows the proposed method achieves a 92.19% detection rate for an average time of 7.62 mins per 24 hrs of recorded 18-channel EEG. A human expert usually requires about 2 hrs of reviewing and labelling per any 24 hrs of recorded EEG and is often assisted by a wide range of auxiliary data such as patient, carer, or nurse inputs. In this prospective analysis, we consider humans’ role as an expert arbiter who confirms to reject each alarm raised by our system. We achieved an average of 56 false alarms per 24 hrs.
Competing Interest Statement
The authors have declared no competing interest.
Footnotes
E-mail: yikai.yang{at}sydney.edu.au, duy.truong{at}sydney.edu.au, christina.maher{at}sydney.edu.au, omid.kavehei{at}sydney.edu.au, armin{at}sydneyneurology.com.au.